{"id":"32938","prompt":"☺️🥸🤠\nPlease make each photo I upload into an independent high-end design poster, no multi-image stitching, each photo output separately. Overall, use a 3:4 vertical composition, the top and bottom areas are strictly 1:1, each occupying 50% of the frame.\n\nThe top half retains the original photo, maintaining the subject's identity, structure, posture, real texture, natural light and shadow, and original color atmosphere, with only slight high-end color grading to give it the texture of an art magazine, independent publication, or exhibition image. To fit the frame, the environmental background can be naturally extended, but the subject must not be stretched, distorted, or changed.\n\nThe bottom half extracts the most recognizable **subject, outline, structure, posture, and narrative relationship** of the photo, translating it into a real, touchable **Physical String-based Systems Map / Tangible Node-link Visualization**. Do not depict the original object directly, but disassemble the subject into a small number of meaningful nodes and relationships: key outlines, structural turns, movement directions, spatial positions, or environmental clues become pushpin-style Nodes, and real strings are used as Edges / Links between them, so that the visual relationships of the original photo manifest again in a physical network, and the identity and structure of the original subject can still be vaguely recognized.\n\nThe composition uses a clear **core node or core relationship** as the visual pivot, and the other nodes naturally unfold around the subject's structure. The strings are not randomly wound but should establish relationships according to the direction, proportion, distance, connection, and narrative logic of the original image; some nodes form radial, convergent, triangular, polygonal, and cross-regional connections, causing a large number of simple relationships to naturally produce **emergent geometry**. The whole is complex yet orderly, with denser central relationships and gradually sparser outer areas, retaining plenty of negative space to avoid filling the entire layout.\n\nThe material must have a real physical installation feel: use small pushpins, stitches, cotton thread or twine, paper labels, handwritten marks, and a real cardboard surface, retaining slight string tension differences, node heights, cross-shading, stitch shadows, and manual errors. The whole is like an art-directed research wall, system design experiment, or information art installation, not a computer-drawn network diagram, nor cyber UI, digital glowing lines, or cheap detective board effects.\n\nThe string uses a **sharp but restrained vermilion, coral red, or warm red** as the primary relationship color, creating visual tension against a large number of natural white, warm white, light grey, or very light backgrounds coordinated with the color temperature of the photo above; pushpins, paper tags, and a few markers can extract local characteristic colors from the photo above for low-area echo. The overall color is clean, modern, and vibrant, avoiding dark brown, dirty old, bloody red horror feel, and excessive retro aging.\n\nText intervenes freely as **Hand-lettered Annotation** in the system, without presetting fixed titles, locations, years, or menu-style information. Based on the subject, action, position, emotion, relationship, or metaphor in the photo, freely generate a few keywords, short sentences, arrows, circled notes, or tiny explanations, and write them directly near nodes, at string intersections, or in blank areas. The font uses a **small, relaxed, slightly research-note-like handwritten annotation font with writing deviations**, making the text look like thoughts naturally left during the observation process, while maintaining the restraint and readability of high-end editorial design.\n\nThe overall presentation is a high-end experimental visual composed of **physical nodes, red strings, relationship mapping, emergent geometry, handwritten annotations, and plenty of white space**. Whether the subject is a person, animal, plant, building, object, vehicle, natural landscape, or complex scene, it should translate \"what it is\" further into \"how its parts relate,\" forming a physical information visualization with research feel, artistic feel, systematicity, and manual warmth. Avoid random red lines, meaningless nodes, full-page chaos, horror crime boards, digital network UI, cartoon pushpins, templated mind maps, and ordinary flowcharts.\n\n😌🥲😘","promptEn":"☺️🥸🤠\nPlease make each photo I upload into an independent high-end design poster, no multi-image stitching, each photo output separately. Overall, use a 3:4 vertical composition, the top and bottom areas are strictly 1:1, each occupying 50% of the frame.\n\nThe top half retains the original photo, maintaining the subject's identity, structure, posture, real texture, natural light and shadow, and original color atmosphere, with only slight high-end color grading to give it the texture of an art magazine, independent publication, or exhibition image. To fit the frame, the environmental background can be naturally extended, but the subject must not be stretched, distorted, or changed.\n\nThe bottom half extracts the most recognizable **subject, outline, structure, posture, and narrative relationship** of the photo, translating it into a real, touchable **Physical String-based Systems Map / Tangible Node-link Visualization**. Do not depict the original object directly, but disassemble the subject into a small number of meaningful nodes and relationships: key outlines, structural turns, movement directions, spatial positions, or environmental clues become pushpin-style Nodes, and real strings are used as Edges / Links between them, so that the visual relationships of the original photo manifest again in a physical network, and the identity and structure of the original subject can still be vaguely recognized.\n\nThe composition uses a clear **core node or core relationship** as the visual pivot, and the other nodes naturally unfold around the subject's structure. The strings are not randomly wound but should establish relationships according to the direction, proportion, distance, connection, and narrative logic of the original image; some nodes form radial, convergent, triangular, polygonal, and cross-regional connections, causing a large number of simple relationships to naturally produce **emergent geometry**. The whole is complex yet orderly, with denser central relationships and gradually sparser outer areas, retaining plenty of negative space to avoid filling the entire layout.\n\nThe material must have a real physical installation feel: use small pushpins, stitches, cotton thread or twine, paper labels, handwritten marks, and a real cardboard surface, retaining slight string tension differences, node heights, cross-shading, stitch shadows, and manual errors. The whole is like an art-directed research wall, system design experiment, or information art installation, not a computer-drawn network diagram, nor cyber UI, digital glowing lines, or cheap detective board effects.\n\nThe string uses a **sharp but restrained vermilion, coral red, or warm red** as the primary relationship color, creating visual tension against a large number of natural white, warm white, light grey, or very light backgrounds coordinated with the color temperature of the photo above; pushpins, paper tags, and a few markers can extract local characteristic colors from the photo above for low-area echo. The overall color is clean, modern, and vibrant, avoiding dark brown, dirty old, bloody red horror feel, and excessive retro aging.\n\nText intervenes freely as **Hand-lettered Annotation** in the system, without presetting fixed titles, locations, years, or menu-style information. Based on the subject, action, position, emotion, relationship, or metaphor in the photo, freely generate a few keywords, short sentences, arrows, circled notes, or tiny explanations, and write them directly near nodes, at string intersections, or in blank areas. The font uses a **small, relaxed, slightly research-note-like handwritten annotation font with writing deviations**, making the text look like thoughts naturally left during the observation process, while maintaining the restraint and readability of high-end editorial design.\n\nThe overall presentation is a high-end experimental visual composed of **physical nodes, red strings, relationship mapping, emergent geometry, handwritten annotations, and plenty of white space**. Whether the subject is a person, animal, plant, building, object, vehicle, natural landscape, or complex scene, it should translate \"what it is\" further into \"how its parts relate,\" forming a physical information visualization with research feel, artistic feel, systematicity, and manual warmth. Avoid random red lines, meaningless nodes, full-page chaos, horror crime boards, digital network UI, cartoon pushpins, templated mind maps, and ordinary flowcharts.\n\n😌🥲😘","promptZh":"☺️🥸🤠\n请将我上传的每一张照片制作成独立的精美设计海报，不要进行多图拼接，每张照片需单独输出。整体构图请使用 3:4 竖构图，顶部和底部区域严格按照 1:1 比例，各占画面 50%。\n\n上半部分保留原始照片，维持主体身份、结构、姿态、真实质感、自然光影及原始色彩氛围，仅进行轻微的高级调色，使其呈现出艺术杂志、独立出版物或展览影像的质感。为适配画幅，环境背景可自然延伸，但主体不得拉伸、变形或改变。\n\n下半部分提取照片中最具辨识度的 **主体、轮廓、结构、姿态及叙事关系**，将其转化为真实的、可触碰的 **实体线艺系统地图 / 有形节点链接可视化**。不要直接描绘原始物体，而是将主体拆解为少量有意义的节点与关系：关键轮廓、结构转折、运动方向、空间位置或环境线索转化为图钉式的“节点”，并使用真实的线绳作为节点间的“边 / 链接”，使原始照片的视觉关系在物理网络中重现，同时仍能隐约辨认出原始主体的身份与结构。\n\n构图需以清晰的 **核心节点或核心关系** 作为视觉支点，其他节点围绕主体结构自然展开。线绳并非随意缠绕，而应根据原图的方向、比例、距离、连接方式及叙事逻辑建立联系；部分节点形成放射状、汇聚状、三角形、多边形及跨区域连接，使大量简单的关系自然产生 **涌现几何感**。整体复杂而有序，中心关系密集，外围区域逐渐稀疏，保留充足的留白，避免填满整个布局。\n\n材质必须具备真实的物理装置感：使用小图钉、缝线、棉线或麻绳、纸质标签、手写标记以及真实的纸板表面，保留轻微的线绳张力差异、节点高度、交叉阴影、缝线投影及手工痕迹。整体效果如同艺术指导下的研究墙、系统设计实验或信息艺术装置，而非电脑绘制的网络图，亦非赛博 UI、数字发光线条或廉价的侦探板效果。\n\n线绳使用 **鲜明但克制的 朱砂红、珊瑚红或暖红色** 作为主要关系色，与大量自然白、暖白、浅灰或极浅的背景形成视觉张力，背景色需与上方照片的色温相协调；图钉、纸签及少量标记可提取上方照片的局部特征色进行小面积呼应。整体色彩干净、现代且充满活力，避免深棕色、脏旧感、血腥恐怖感以及过度的复古老化效果。\n\n文字作为 **手写标注** 在系统中自由介入，不预设固定的标题、地点、年份或菜单式信息。根据照片中的主体、动作、位置、情绪、关系或隐喻，自由生成少量关键词、短句、箭头、圈注或简短说明，并直接书写在节点附近、线绳交叉处或空白区域。字体采用 **小巧、放松、带有书写偏差的类研究笔记手写体**，使文字看起来像是观察过程中自然留下的思考，同时保持高端编辑设计所需的克制与可读性。\n\n整体呈现为一种由 **物理节点、红线、关系映射、涌现几何、手写标注及充足留白** 构成的高端实验性视觉作品。无论主体是人物、动物、植物、建筑、物体、车辆、自然景观还是复杂场景，都应将“它是什么”进一步转化为“其各部分如何关联”，从而形成一种兼具研究感、艺术感、系统性与手工温度的实体信息可视化作品。避免随机的红线、无意义的节点、满屏混乱、恐怖犯罪板、数字网络 UI、卡通图钉、模板化思维导图以及普通的流程图。\n\n😌🥲😘"}